🧑‍🔬 Weigao Sun

🏛️ Affiliations

🔬Shanghai Artificial Intelligence LaboratoryShanghai · China2023–2026 · 13 paperscurrent🎓Huazhong University of Science and TechnologyWuhan · China2018–2020 · 9 papers🔬State Key Laboratory of Digital Manufacturing Equipment and TechnologyWuhan · China2019 · 5 papers

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

🧭 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. A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond (2025 · 55 citations)
   Large Reasoning Models (LRMs) such as DeepSeek-R1, OpenAI o1/o3 and QwQ gain accuracy by writing long chain-of-thought (CoT) traces before answering.
2. TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer (2023 · 33 citations)
   Linear attention promises to remove the quadratic cost of softmax attention. In practice, earlier linear-attention models have trailed Transformers in language-modeling quality and rarely ran faster on real hardware. The authors close this gap with TransNormerLLM, a redesigned version of their TransNormer…
3. Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models (2024 · 31 citations)
   Linear attention should cost O(n) instead of the O(n²) of softmax attention. In causal language modeling, however, existing implementations lose this advantage: the kernel trick needs a cumulative summation (cumsum) that parallelizes poorly on GPUs. Lightning Attention-1 had already reduced the memory-I/O bottleneck…
4. Liger: Linearizing Large Language Models to Gated Recurrent Structures (2025 · 9 citations)
   Transformer LLMs have attention cost that grows quadratically with sequence length, and their KV cache keeps growing during generation.
5. MoM: Linear Sequence Modeling with Mixture-of-Memories (2025 · 7 citations)
   Linear sequence models such as linear attention, state space models and linear RNNs train in linear time and run inference with constant cost.

All works

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

1. A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and BeyondarXiv:2503.21614Xiaoye Qu, Yafu Li, Zhao-Chen Su, et al.2025 · 55 citations
2. TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormerarXiv:2307.14995Zhen Qin, Dong Li, Weigao Sun, et al.2023 · 33 citations
3. Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language ModelsarXiv:2401.04658Zhen Qin, Weigao Sun, Dong Li, et al.2024 · 31 citations
4. Linear Attention Sequence Parallelism ↗arXiv:2404.02882 · no summary yetWeigao Sun et al.2024 · 12 citations
5. Liger: Linearizing Large Language Models to Gated Recurrent StructuresarXiv:2503.01496Disen Lan, Weigao Sun, Jiaxi Hu, et al.2025 · 9 citations
6. MoM: Linear Sequence Modeling with Mixture-of-MemoriesarXiv:2502.13685Jusen Du, Weigao Sun, Disen Lan, et al.2025 · 7 citations
7. CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models ↗Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetXiaqiang Tang et al.2025 · 4 citations

🤝 Co-authors here

12 of 20 co-authors with a page, the most papers together first.

• Disen Lan ×2
• Dong Li ×2
• Jiaxi Hu ×2
• Jusen Du ×2
• Weixuan Sun ×2
• Xuyang Shen ×2
• Yiran Zhong ×2
• Yu Cheng ×2
• Zhen Qin ×2
• Daizong Liu
• Dongrui Liu
• Ganqu Cui

Venues

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

• Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

🔗 Cited by

Papers of our library cite their works 188 times (of the 149,439 papers whose bibliographies we read); 44 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/weigao-sun/