Junzhe Chen.

I am a Ph.D. student in Computer Science at Tianjin University. My research sits at the intersection of computer vision and multimodal learning.

I am particularly interested in object-centric video understanding: preserving identity through occlusion and change, grounding temporal reasoning in visual evidence, and designing token-efficient interfaces for Video-LLMs. My earlier work spans tiny-object detection and mixed-precision model quantization.

• 01Video understanding
• 02Vision-language models
• 03Object-centric learning
• 04Efficient deep learning