Yean Cheng
Yean Cheng has 2 papers in our library, in 2024, most of them on Language models & pretraining, Evaluation & benchmarks, Vision & language; often with Ming Ding, Shiyu Huang, Weihan Wang.
OpenAlex · ORCID · h-index 5 · 13 works · 82 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 455 times in our library · ⭐ Paper Stars ranking: #7247
Affiliations
Fields, topics and concepts
📚 Shelves 2The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksComputer Vision and Pattern Recognition · 2 works
🧭 Topics 3Research subjects and languages the work is about.Evaluation & benchmarks · 1 workLanguage models & pretraining · 1 workVision & language · 1 work
Works by year
2020s
Papers
- LVBench: An Extreme Long Video Understanding Benchmark (2024 · 89 citations)
Most video benchmarks for multimodal large language models (MLLMs) test short clips or single images, so they say little about whether a model can follow events over hours. - CogVLM2: Visual Language Models for Image and Video Understanding (2024 · 52 citations)
Text-only LLMs cannot use visual input. Existing vision-language models often have three weaknesses: they connect image features to the LLM only superficially, high-resolution inputs make them expensive, and they lose track of timing in videos.
Co-authors here
- Ming Ding ×2
- Shiyu Huang ×2
- Weihan Wang ×2
- Wenyi Hong ×2
- Bin Xu
- Ji Qi
- Jie Tang
- Junhui Ji
- Lei Zhao
- Qingsong Lv
- Wenmeng Yu
- Xiaohan Zhang
Venues
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/yean-cheng/