🧑‍🔬 Yibo Yan

🏛️ Affiliations

🎓The Hong Kong University of Science and Technology (Guangzhou)Guangzhou · China2026 · 4 paperscurrent🎓Hong Kong University of Science and TechnologyHong Kong · China2026 · 3 paperscurrent

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. ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection (2026 · 23 citations)
   Existing math benchmarks for multimodal large language models (MLLMs) mostly check whether a model can solve a problem.
2. Position: LLMs Can be Good Tutors in English Education (2025 · 9 citations)
   This is a position paper. It runs no experiments and introduces no dataset. The authors argue that current LLM uses in English teaching mostly reuse standard NLP task framings and ignore educational methodology. They contend that LLMs can work as tutors that support human teachers rather than replace them. They…
3. CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring (2026 · 4 citations)
   Multimodal writing tasks ask students to argue from images such as charts. Scoring them automatically is hard. Classic AES systems depend on handcrafted features and cannot process images. Single-MLLM scorers tend to invent justifications and grade more harshly than human raters. CAFES addresses this by dividing…
4. GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning (2026 · 2 citations)
   Multimodal LLMs often fail at multi-step math over images because one perception or logic slip in a single step derails the whole solution.
5. Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework (2026 · 2 citations)
   Multi-vector models for Visual Document Retrieval (VDR), such as those in the ColPali family, represent each page as hundreds or thousands of patch embeddings.
6. Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering (2026 · 1 citation)
   Multimodal LLMs often describe objects that are not in the image. The authors trace this to models trusting language-based expectations over what the image actually shows. They propose Vision-Language Introspection (VLI), a training-free method applied at inference time.

🤝 Co-authors here

12 of 23 co-authors with a page, the most papers together first.

• Xuming Hu ×4
• Xin Zou ×3
• Jiahao Huo ×2
• Jiamin Su ×2
• Kun Wang ×2
• Shen Wang ×2
• Shuliang Liu ×2
• Boyan Li
• Deqing Zou
• Hai-Tao Zheng
• Han Zhang
• Hang Li

Venues

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

• Workshop on Advances in Language and Vision Research (ALVR) ×2: ALVR 2026 ×2
• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025

🔗 Cited by

Papers of our library cite their works 31 times (of the 149,439 papers whose bibliographies we read); 6 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/yibo-yan/