Pu Jian
Pu Jian has 2 papers in our library, in 2025, most of them on Language models & pretraining, Vision & language; often with Jiajun Zhang, Shuo Ren, Can Xie.
OpenAlex · ORCID · Wikidata · h-index 29 · 196 works · 3,229 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 27 times in our library · ⭐ Paper Stars ranking: #10167
Affiliations
Fields, topics and concepts
📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksDecision Sciences · 1 workInformation Systems and Management · 1 workComputer Vision and Pattern Recognition · 1 work
🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 1 workVision & language · 1 work
Works by year
2020s
Papers
- Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents (2025 · 24 citations)
This survey examines LLM-based scientific agents. These systems go beyond general-purpose chat or coding agents by drawing on domain knowledge, calling specialized tools such as simulators, APIs and lab instruments, and handling data like molecular structures or biological sequences. Earlier surveys sorted such… - Teaching Vision-Language Models to Ask: Resolving Ambiguity in Visual Questions (2025 · 13 citations)
Vision-language models (VLMs) often receive vague visual questions and respond with a guess. Earlier work handled this by rewriting the question. This paper instead treats ambiguity as something to resolve through dialogue: the model should recognise an unclear question, ask the user a clarifying question, and use…
Co-authors here
Venues
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/pu-jian/