Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices
Published in CVPR 2025 - IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025
Junyan Lin
PhD Student in Computer Science at The Hong Kong Polytechnic University. Research interests: Multimodal Large Language Models, Embodied AI.
- Hong Kong, China
- The Hong Kong Polytechnic University
- Google Scholar
- GitHub