Papers
1
Total Citations
4
H-Index
1
About
Yukun Li is a leading researcher in the field of continual learning for vision-language models (VLMs), with a particular focus on enabling AI systems to adapt to open-domain environments. Their most notable contribution, the CoLeCLIP framework, addresses the critical challenge of continual learning in VLMs by introducing joint task prompt and vocabulary learning. This work, published in 2025 and already garnering 4 citations, allows models to perform continual updating and inference on streams of datasets from diverse seen and unseen domains with novel classes—a capability essential for real-world AI deployment. Li’s research sits at the intersection of computer vision, natural language processing, and lifelong learning, tackling the fundamental problem of catastrophic forgetting in open-domain settings. By developing methods that enable models to learn continuously without forgetting previously acquired knowledge, Li is paving the way for more adaptable and robust AI systems. Their work on CoLeCLIP represents a significant step toward creating vision-language models that can operate effectively in dynamic, ever-changing environments, making it highly relevant for researchers working on continual learning, multimodal AI, and domain adaptation.
Research Focus
Key Achievements
Top Papers
- 1