--- title: "Ruihua Song — author profile and papers — Elamur Research" description: "Ruihua Song, Renmin University of China: 5 papers on Elamur Research (2023–2025), h-index 35 — affiliations, topics, co-authors and who…" canonical: "https://research.elamur.ai/free/en/authors/ruihua-song/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/ruihua-song/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Ruihua Song # Ruihua Song Ruihua Song has 5 papers in our library, in 2023–2025, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/), [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/); often with [Wayne Xin Zhao](https://md.research.elamur.ai/free/en/authors/wayne-xin-zhao/), [Kun Zhou](https://md.research.elamur.ai/free/en/authors/kun-zhou/), [Yankai Lin](https://md.research.elamur.ai/free/en/authors/yankai-lin/). 5 papers in our library · 2023–2025 [OpenAlex](https://openalex.org/A5101505570) · [ORCID](https://orcid.org/0000-0001-6036-9035) · [Wikidata](https://www.wikidata.org/wiki/Q131166689) · [**h-index 35**](https://openalex.org/authors/A5101505570) · [151 works](https://openalex.org/works?filter=author.id:A5101505570) · [4,505 citations](https://openalex.org/works?filter=author.id:A5101505570&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 5 works in our library](https://md.research.elamur.ai/free/en/authors/ruihua-song/#papers) · [🔗 Cited 118 times in our library](https://md.research.elamur.ai/free/en/authors/ruihua-song/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #7365](https://md.research.elamur.ai/free/en/paper-stars/page/74/#star-7365) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Ruihua+Song) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Ruihua+Song) · [dblp](https://dblp.org/search?q=Ruihua+Song) · [ACL Anthology](https://aclanthology.org/search/?q=Ruihua+Song) ## Affiliations [🎓**Renmin University of China** Beijing · China 2019–2026 · 67 papers*current*](https://md.research.elamur.ai/free/en/universities/renmin-university-of-china/) · [🏢**Microsoft Research Asia** Beijing · China 2003–2020 · 43 papersEmployment since 2003 · Lead Researcher](https://md.research.elamur.ai/free/en/companies/microsoft-research-asia/) · [🏢**Microsoft** Redmond · United States 2009–2020 · 16 papers](https://md.research.elamur.ai/free/en/companies/microsoft/) · [🎓**Shanghai Jiao Tong University** Shanghai · China 2006–2011 · 5 papersEducation 2006–2011 · PhD, Computer Science](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) · [🎓**Tsinghua University** Beijing · China 1996–2003Education 1996–2000 · BS., Computer Science and TechnologyEducation 2000–2003 · MS., Computer Science and Technology](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) 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. 📚 Shelves 7 The field of science this work belongs to (OpenAlex fields).[Computer Science · 5 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 5 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Information Systems · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · [Computer Vision and Pattern Recognition · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Computational Theory and Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) 🧭 Topics 4 Research subjects and languages the work is about.[Language models & pretraining · 3 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Reasoning · 2 works](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Efficient models & compression · 1 work](https://md.research.elamur.ai/free/en/topics/efficient-models/) · [Vision & language · 1 work](https://md.research.elamur.ai/free/en/topics/multimodal/) ## Works by year ### 2020s [**2025** 4 papers](https://md.research.elamur.ai/free/en/authors/ruihua-song/year/2025/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/ruihua-song/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[User Behavior Simulation with Large Language Model based Agents](https://md.research.elamur.ai/free/en/papers/wang-2023-user-behavior-simulation-large-language/)** *(2023 · 64 citations)* Building synthetic user data for recommender systems and social platforms is hard. Earlier simulators reduce human choice to simple scoring functions, need real logs to train, and usually cover only one environment. This work tests whether large language models can act as believable users with little or no real data.… 2. **[Towards Effective and Efficient Continual Pre-training of Large Language Models](https://md.research.elamur.ai/free/en/papers/chen-2025-effective-efficient-continual-pre-training/)** *(2025 · 29 citations)* Continual pre-training (CPT) is a common way to adapt an LLM to new languages or domains. Its main risk is catastrophic forgetting, where the model gains new skills but loses old ones. The authors give a fully open CPT recipe for Llama-3 (8B) that targets two weaknesses: Chinese language ability and multidisciplinary… 3. **[Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains](https://md.research.elamur.ai/free/en/papers/tan-2025-think-silently-think-fast-dynamic/)** *(2025 · 19 citations)* Chain-of-Thought prompting improves LLM accuracy on math problems, but it produces long token sequences that are slow and costly to generate. 4. **[What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning](https://md.research.elamur.ai/free/en/papers/du-2025-what-makes-good-visual-instructions/)** *(2025 · 13 citations)* The paper asks which properties of visual instruction data actually help Multi-modal Large Language Models (MLLMs) generalize, since earlier collections had never been compared under the same backbone and training setup. 5. **[ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization](https://md.research.elamur.ai/free/en/papers/chen-2025-reform-reflective-autoformalization-prospective-bounded/)** *(2025 · 8 citations)* Autoformalization turns natural-language math problems into Lean statements that a machine can check. Current LLMs usually produce code that compiles, but the statements often change the problem's meaning. The authors argue this happens because models translate in one shot and never review their own output. ReForm… ## All works 6 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. [**User Behavior Simulation with Large Language Model based Agents arXiv:2306.02552**Lei Wang, Jingsen Zhang, Hao Yang, et al.*2023 · 64 citations*](https://md.research.elamur.ai/free/en/papers/wang-2023-user-behavior-simulation-large-language/) 2. **[Intelligent Agents with LLM-based Process Automation ↗](https://doi.org/10.1145/3637528.3671646) ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · no summary yet**Yanchu Guan et al.*2024 · 60 citations* 3. **[Towards Effective and Efficient Continual Pre-training of Large Language Models](https://md.research.elamur.ai/free/en/papers/chen-2025-effective-efficient-continual-pre-training/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Jie Chen, Zhipeng Chen, Jiapeng Wang, et al.*2025 · 29 citations* 4. **[Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains](https://md.research.elamur.ai/free/en/papers/tan-2025-think-silently-think-fast-dynamic/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Wenhui Tan, Jiaze Li, Jianzhong Ju, et al.*2025 · 19 citations* 5. **[What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning](https://md.research.elamur.ai/free/en/papers/du-2025-what-makes-good-visual-instructions/) [International Conference on Computational Linguistics (COLING)](https://md.research.elamur.ai/free/en/venues/coling/)**Yifan Du, Hangyu Guo, Kun Zhou, et al.*2025 · 13 citations* 6. [**ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization arXiv:2510.24592**Guoxin Chen, Jing Wu, Xinjie Chen, et al.*2025 · 8 citations*](https://md.research.elamur.ai/free/en/papers/chen-2025-reform-reflective-autoformalization-prospective-bounded/) ## Co-authors here 12 of 30 co-authors with a page, the most papers together first. - [Wayne Xin Zhao](https://md.research.elamur.ai/free/en/authors/wayne-xin-zhao/) ×4 - [Kun Zhou](https://md.research.elamur.ai/free/en/authors/kun-zhou/) ×2 - [Yankai Lin](https://md.research.elamur.ai/free/en/authors/yankai-lin/) ×2 - [Zhicheng Dou](https://md.research.elamur.ai/free/en/authors/zhicheng-dou/) ×2 - [Chengxi Li](https://md.research.elamur.ai/free/en/authors/chengxi-li/) - [Dayiheng Liu](https://md.research.elamur.ai/free/en/authors/dayiheng-liu/) - [Guoxin Chen](https://md.research.elamur.ai/free/en/authors/guoxin-chen/) - [Hangyu Guo](https://md.research.elamur.ai/free/en/authors/hangyu-guo/) - [Hao Yang](https://md.research.elamur.ai/free/en/authors/hao-yang/) - [Ji-Rong Wen](https://md.research.elamur.ai/free/en/authors/ji-rong-wen/) - [Jiakai Tang](https://md.research.elamur.ai/free/en/authors/jiakai-tang/) - [Jian Luan](https://md.research.elamur.ai/free/en/authors/jian-luan/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/): [ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/) - [International Conference on Computational Linguistics (COLING)](https://md.research.elamur.ai/free/en/venues/coling/): [COLING 2025](https://md.research.elamur.ai/free/en/venues/coling/2025/) - [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/): [NeurIPS 2025](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/) - ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) ## Cited by Papers of our library cite their works 118 times (of the 149,439 papers whose bibliographies we read); [38 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/ruihua-song/cited-by/). Updated 2 November 2026