🧑‍🔬 Jingxuan Wei

🏛️ Affiliations

🎓University of Chinese Academy of SciencesBeijing · China2020–2026 · 34 papersEducation 2020–2025 · Phdcurrent🏛️Chinese Academy of SciencesBeijing · China2020–2026 · 32 paperscurrent🏢Shenyang Institute of Computing TechnologyShenyang · China2020–2026 · 30 paperscurrent🎓Xidian UniversityXi'an · China2006–2024 · 27 papers🎓Nanjing University of Information Science and TechnologyNanjing · China2025 · 2 papers🎓Nagoya UniversityNagoya · Japan2015–2016 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 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. MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification (2025 · 19 citations)
   The paper targets two gaps in multimodal math reasoning. There is no strong verifier for checking answers from multimodal LLMs, and there is little long chain-of-thought (CoT) training data with images. The authors build two 7B models. MM-Verifier is an outcome reward model that judges whether a solution to an…
2. GenProve: Learning to Generate Text with Fine-Grained Provenance (2026)
   Citations in LLM answers often point only to whole documents. They do not show which sentence backs a claim or how that sentence is used, so checking the answer stays hard. The authors define a task called Generation-time Fine-grained Provenance. The model writes an answer and, for each sentence, emits structured…
3. Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration (2026)
   Most Text-to-SQL benchmarks test one-shot translation of a fixed question into a read-only query. Real database work is different: users refine goals over several turns and often need to change data, not just read it. The authors introduce DySQL-Bench to evaluate LLM agents in this setting. It contains 1,072…
4. Training Verifier to Assessing Complex Real-World Tool-Use Trajectories (2026)
   LLM agents that handle multi-turn customer-service style tasks need training dialogues that reflect real user–agent collaboration.

🤝 Co-authors here

12 of 13 co-authors with a page, the most papers together first.

• Bihui Yu ×4
• Hao Liang ×3
• Linzhuang Sun ×3
• Wentao Zhang ×3
• Fan Yang ×2
• Tianpeng Li ×2
• Tianyu Guo ×2
• Bin Cui
• Chenzheng Zhu
• Junnan Zhu
• Mingyang Chen
• Ruitong Liu

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) ×2: ACL 2026, ACL 2025
• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2

🔗 Cited by

Papers of our library cite their works 15 times (of the 149,439 papers whose bibliographies we read); 5 citing papers with a page here →.

Updated 1 November 2026

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