🧑‍🔬 Wenhao Li

🏛️ Affiliations

🎓Shandong Normal UniversityJinan · China2024–2026 · 14 paperscurrent🎓Huazhong University of Science and TechnologyWuhan · China2025–2026 · 6 paperscurrent🎓Tongji UniversityShanghai · China2025–2026 · 4 paperscurrent🎓Beijing Normal-Hong Kong Baptist UniversityZhuhai · China2024–2026 · 2 paperscurrent🎓Swinburne University of TechnologyMelbourne · Australia2010–2015 · 23 papers🎓University of Southern CaliforniaLos Angeles · United States2018–2023 · 10 papers🎓University of South AustraliaAdelaide · Australia2017–2019 · 6 papers🎓East China Normal UniversityShanghai · China2006–2022 · 5 papers🎓Shandong UniversityJinan · China2009–2016 · 4 papers🎓Shanghai Normal UniversityShanghai · China2007–2010 · 4 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 31 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. LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations (2023 · 32 citations)
   The paper asks whether GPT-style LLMs can handle the Abstraction and Reasoning Corpus (ARC), a benchmark of grid puzzles built on human "core knowledge" priors such as objectness, counting and basic geometry.
2. Agentic Episodic Control (2026)
   Episodic reinforcement learning agents store past experiences in an external memory to learn faster. The authors argue that such agents have two weaknesses. First, small trainable encoders produce narrow state embeddings, which they call a representation bottleneck. Second, the agent queries memory with KNN at every…
3. On-policy Reinforcement Fine-tuning with Offline reward for Multi-step Embodied Planning (2026)
   Vision-language models handle static perception well but break down when they must plan many actions in an interactive environment.

All works

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

1. Stylistic Chinese Poetry Generation via Unsupervised Style Disentanglement ↗Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · no summary yetCheng Yang et al.2018 · 74 citations
2. LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based RepresentationsarXiv:2305.18354Yudong Xu, Wenhao Li, Pashootan Vaezipoor, et al.2023 · 32 citations
3. Agentic Episodic ControlFindings of the Association for Computational LinguisticsXidong Yang, Wenhao Li, Junjie Sheng, et al.2026
4. On-policy Reinforcement Fine-tuning with Offline reward for Multi-step Embodied PlanningAnnual Meeting of the Association for Computational Linguistics (ACL)Di Wu, Jiaxin Fan, Chloe Gu, et al.2026

🤝 Co-authors here

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

• Bo Jin
• Di Wu
• Guanbo Wang
• Scott Sanner
• Xiangfeng Wang

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): ACL 2026
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

🔗 Cited by

Papers of our library cite their works 45 times (of the 149,439 papers whose bibliographies we read); 4 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/wenhao-li/