Papers
1
Total Citations
3
H-Index
1
About
Qiying Yu is a leading researcher in multimodal artificial intelligence, with a primary focus on advancing large multimodal models through innovative learning paradigms. Their most notable contribution is the development of a unified algorithm that extends next-token prediction—the cornerstone of large language models—to seamlessly integrate and generate across text, images, and video. This work, detailed in their highly cited 2026 paper "Multimodal learning with next-token prediction for large multimodal models," addresses a fundamental challenge in AI: enabling a single model to learn from and produce outputs across diverse modalities. By bridging the gap between language-centric architectures and multimodal understanding, Yu's research has opened new pathways for more versatile and efficient AI systems. With 3 citations already, this work is gaining recognition for its potential to redefine how machines process and generate complex, multi-format information. Yu's contributions are particularly valuable for students and researchers seeking to understand the next frontier of AI—where text, images, and video converge under a unified learning framework.
Research Focus
Key Achievements
Top Papers
- 1