Guang Liu

Beijing Academy of Artificial Intelligence

Papers

1

Total Citations

3

H-Index

1

About

Guang Liu is a rising researcher in artificial intelligence, whose work focuses on advancing multimodal learning and large-scale foundation models. His primary research interests lie at the intersection of natural language processing and computer vision, particularly in developing unified algorithms that can seamlessly learn from and generate across text, images, and video. Liu’s most notable contribution is his pioneering work on extending the next-token prediction paradigm—the core mechanism behind large language models—to the multimodal domain. This approach addresses a fundamental challenge in AI: enabling a single model to process and produce diverse data types without task-specific architectures. His 2026 paper on this topic has already garnered early citations, signaling its potential to influence future multimodal system design. By bridging the gap between language-centric and vision-centric models, Liu’s research promises to accelerate progress toward more general and capable artificial intelligence. His work is particularly relevant for students and researchers interested in the next generation of multimodal AI, where unified learning algorithms could unlock new capabilities in content generation, robotics, and human-computer interaction.

Research Focus

Key Achievements

1
H-Index
1
Papers
3
Total Citations
3
Avg Citations/Paper
🏆 Most Cited Paper
Multimodal learning with next-token prediction for large multimodal models
3 citations · 2026
📈 Most Prolific Year: 2026 (1 Papers)
🤝 Key Collaborators: 24
🏛 Institutions: Beijing Academy of Artificial Intelligence

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago