From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 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.

📚 Shelves 5Arts and Humanities · 3 works Computer Science · 3 works Artificial Intelligence · 3 works Language and Linguistics · 3 works Hardware and Architecture · 2 works

🧭 Topics 2Language models & pretraining · 1 work Reasoning · 1 work

💡 Concepts 1Retrieval-augmented generation · 1 work

Works by year

2020s

20241 paper 20232 papers

Papers

The most cited first (OpenAlex and our library).

SGLang: Efficient Execution of Structured Language Model Programs (2023 · 729 citations)
Modern LLM applications such as agents, few-shot evaluation, tree-of-thought search, RAG and JSON extraction rarely make a single model call.
S-LoRA: Serving Thousands of Concurrent LoRA Adapters (2023 · 80 citations)
Organizations increasingly fine-tune one base LLM into many task-specific LoRA variants, but serving them all at once is poorly supported.
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models (2024 · 67 citations)
Prompting strategies for LLM reasoning fall into two camps. Single-query methods such as CoT or few-shot prompting rely on hand-made, task-specific exemplars. Multi-query methods such as ToT and GoT explore many reasoning paths but are computationally expensive. Neither reuses general lessons from problems already…

All works

17 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

SGLang: Efficient Execution of Structured Language Model ProgramsConference on Neural Information Processing Systems (NeurIPS)Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, et al.2023 · 729 citations
S-LoRA: Serving Thousands of Concurrent LoRA AdaptersMLSys 2024Ying Sheng, Shiyi Cao, Dacheng Li, et al.2023 · 80 citations
NVILA: Efficient Frontier Visual Language Models ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetZhijian Liu et al.2025 · 73 citations
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language ModelsConference on Neural Information Processing Systems (NeurIPS)Ling Yang, Zhaochen Yu, Tianjun Zhang, et al.2024 · 67 citations
Fairness in Serving Large Language Models ↗arXiv (Cornell University) · no summary yetYing Sheng et al.2023 · 62 citations
LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters! ↗arXiv:2502.07374 · no summary yetDacheng Li et al.2025 · 56 citations
MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs ↗ASPLOS 2025 · no summary yetShiyi Cao et al.2024 · 51 citations
NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM Inference ↗arXiv:2411.01142 · no summary yetXuanlin Jiang et al.2024 · 37 citations
MoE-L ightning : High-Throughput MoE Inference on Memory-constrained GPUs ↗ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · no summary yetShiyi Cao et al.2025 · 28 citations
Autonomous biomedical research with an artificial intelligence agent ↗Science · no summary yetKexin Huang et al.2026 · 26 citations
S*: Test Time Scaling for Code Generation ↗Findings of the Association for Computational Linguistics: EMNLP 2025 · no summary yetDacheng Li et al.2025 · 26 citations
K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model ↗arXiv:2602.19128 · no summary yetShiyi Cao et al.2026 · 21 citations
Language Models Can Easily Learn to Reason from Demonstrations ↗Findings of the Association for Computational Linguistics: EMNLP 2025 · no summary yetDacheng Li et al.2025 · 14 citations
Optimizing LLM Queries in Relational Data Analytics Workloads ↗arXiv:2403.05821 · no summary yetShu Liu et al.2024 · 12 citations
WorldModelBench: Judging Video Generation Models As World Models ↗neural information processing systems · no summary yetDacheng Li et al.2025 · 11 citations
SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent ↗arXiv (Cornell University) · no summary yetShiyi Cao et al.2025 · 8 citations
Locality-aware Fair Scheduling in LLM Serving ↗arXiv (Cornell University) · no summary yetShiyi Cao et al.2025 · 7 citations

Co-authors here

12 of 16 co-authors with a page, the most papers together first.

Venues

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

Conference on Neural Information Processing Systems (NeurIPS) ×2: NeurIPS 2024, NeurIPS 2023
Findings of the Association for Computational Linguistics: EMNLP 2025 ×2
ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)
ASPLOS 2025
IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings
MLSys 2024
Science
neural information processing systems

Cited by

Papers of our library cite their works 1,035 times (of the 149,439 papers whose bibliographies we read); 116 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/shiyi-cao/

🧑‍🔬 Shiyi Cao

🏛️ Affiliations

🧭 Fields, topics and concepts

📅 Works by year

2020s

📄 Papers

All works

🤝 Co-authors here

Venues

🔗 Cited by

Shiyi Cao

Affiliations

Fields, topics and concepts

Works by year

Papers

Co-authors here

Cited by