🧑‍🔬 Zijian Wu

🏛️ Affiliations

🎓Anhui University of Traditional Chinese MedicineHefei · China2025–2026 · 3 paperscurrent🎓Tsinghua UniversityBeijing · China2024–2026 · 2 paperscurrent🎓Peking UniversityBeijing · China2026 · 1 papercurrent🎓Zhejiang Sci-Tech UniversityHangzhou · China2026 · 1 papercurrent🎓Nanjing University of Science and TechnologyNanjing · China2022–2025 · 7 papers🎓National University of SingaporeSingapore · Singapore2023–2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 7 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. InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning (2024 · 90 citations)
   InternLM-Math is a family of open math-specialised LLMs from Shanghai AI Laboratory and partner universities.
2. Lean Workbook: A large-scale Lean problem set formalized from natural language math problems (2024 · 80 citations)
   Large language models do well on informal math but poorly on formal theorem proving in Lean. A main reason is the lack of formal training data: MiniF2F is small, and Mathlib mostly covers foundational theorems rather than competition problems. The authors built an active-learning autoformalization pipeline that…
3. InternLM2.5-StepProver: Advancing Automated Theorem Proving via Critic-Guided Search (2024 · 59 citations)
   Most LLM theorem provers for LEAN build a proof one tactic at a time. They pick which proof state to expand next using the prover's own log-probabilities. That signal gets unreliable as proofs get longer, so these systems rarely find deep proofs. The authors add a separate critic model that scores each proof state.…
4. SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis (2026 · 3 citations)
   SynthRL tackles a data bottleneck in reinforcement learning with verifiable rewards (RLVR) for vision-language models. Curated question–answer pairs are costly, and data selection alone cannot go beyond the pool that already exists. The authors instead generate new training items. Their pipeline has three steps:
5. Intern-S1-MO: Long-horizon Reasoning Agent for Olympiad?Level Mathematical Problem Solving (2025 · 1 citation)
   Even strong Large Reasoning Models (LRMs) struggle on IMO-level problems. The exploration these problems need outgrows a single 64K–128K context window, and earlier workarounds were mostly prompt-only pipelines on proprietary models. The authors present Intern-S1-MO, an agent framework that splits problem solving…

🤝 Co-authors here

12 of 24 co-authors with a page, the most papers together first.

• Huaiyuan Ying ×3
• Dahua Lin ×2
• Kai Chen ×2
• Wenwei Zhang ×2
• Zhejian Zhou ×2
• Zheng Yuan ×2
• Haiteng Zhao
• Hang Yan
• Jinjie Ni
• Junhao Shen
• Kuikun Liu
• Lingkai Kong

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: Findings of the Association for Computational Linguistics 2026
• Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2024

🔗 Cited by

Papers of our library cite their works 223 times (of the 149,439 papers whose bibliographies we read); 48 citing papers with a page here →.

Updated 2 November 2026

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