🧑‍🔬 Yujun Cai

🏛️ Affiliations

🎓The University of QueenslandBrisbane · Australia2024–2026 · 56 papersEmployment since 2024current🎓Nanyang Technological UniversitySingapore · Singapore2017–2024 · 29 papersEducation 2017–2021 · PhD.🏢Ant GroupHangzhou · China2025–2026 · 5 papers🏢MetaMenlo Park · United States2022–2025 · 3 papersEmployment 2022–2024 · Research Scientist, Meta Reality Lab🎓University of California, MercedMerced · United States2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 8 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. DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning (2025 · 8 citations)
   Locating the on-screen element that a natural-language command refers to (GUI grounding) is difficult. High-resolution screenshots are crowded with distractors, and vision-language models tend to favour visible text over icons, even when an icon is the real target. DiMo-GUI is a training-free, plug-and-play inference…
2. Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models (2025 · 6 citations)
   Large Audio-Language Models (LALMs) turn a recording into a fixed set of embeddings once. After that step they cannot go back to the signal. Because of this, they perform poorly when audio is noisy or degraded, or when a task depends on fine acoustic detail. The authors propose Thinking-with-Sound (TwS), a framework…
3. Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLMs (2025 · 5 citations)
   Large Reasoning Models (LRMs) such as DeepSeek-R1 produce long Chain-of-Thought traces, yet they often behave erratically.
4. Vulnerability of LLMs to Vertically Aligned Text Manipulations (2025 · 5 citations)
   The paper asks whether decoder-based LLMs are as vulnerable as encoder models like BERT when some words in a text are written vertically, one character per line.
5. Beyond Query Bias: Candidate-Aware Iterative Refinement for Zero-Shot Composed Image Retrieval (2026)
   The paper addresses a weakness in Zero-Shot Composed Image Retrieval (ZS-CIR), where a system must find a target image from a reference image plus a modification text without task-specific training.
6. Mitigating Coordinate Prediction Bias from Positional Encoding Failures (2026)
   Multimodal LLMs that output click coordinates as digit strings often drift on high-resolution screenshots, because visual positional encodings (VPEs) lose grounding strength in long visual contexts.

All works

7 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

1. A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetYujun Cai et al.2021 · 68 citations
2. DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual ReasoningConference on Empirical Methods in Natural Language Processing (EMNLP)Hang Wu, Hongkai Chen, Yujun Cai, et al.2025 · 8 citations
3. Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language ModelsarXiv:2509.21749Zhen Xiong, Yujun Cai, Zhecheng Li, et al.2025 · 6 citations
4. Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLMsConference on Empirical Methods in Natural Language Processing (EMNLP)Zhen Xiong, Yujun Cai, Zhecheng Li, et al.2025 · 5 citations
5. Vulnerability of LLMs to Vertically Aligned Text ManipulationsAnnual Meeting of the Association for Computational Linguistics (ACL)Zhecheng Li, Yiwei Wang, Bryan Hooi, et al.2025 · 5 citations
6. Beyond Query Bias: Candidate-Aware Iterative Refinement for Zero-Shot Composed Image RetrievalFindings of the Association for Computational LinguisticsNan Sun, Jing Tang, Lei Sun, et al.2026
7. Mitigating Coordinate Prediction Bias from Positional Encoding FailuresFindings of the Association for Computational LinguisticsXingjian Tao, Yiwei Wang, Yujun Cai, et al.2026

🤝 Co-authors here

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

• Yiwei Wang ×5
• Zhecheng Li ×3
• Zhen Xiong ×3
• Jing Tang ×2
• Bryan Hooi
• Chang Liu
• Hefei Ling
• Kai Han
• Kai-Wei Chang
• Nanyun Peng
• Xiangxiang Chu
• Yuxing Lu

Venues

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

• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×2: EMNLP 2025 ×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 2025
• IEEE/CVF International Conference on Computer Vision (ICCV)

🔗 Cited by

Papers of our library cite their works 24 times (of the 149,439 papers whose bibliographies we read); 9 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/yujun-cai/