3 papers
cs.LG2026
Improving Parameter Utilization by Sharing Neural Experts Across Layers in Transformers
Dian Jiao, Jiaxin Duan, Shuai Zhao +3
Transformer-based large language models often suffer from inter-layer parameter redundancy, where functional transformations are redundantly learned across network depths. We propo…
cs.CL2026
ViCo: Visual-oriented Coding with Self-Reflection for Chart Replication
Jiaxin Duan, Dian Jiao Shuai Zhao, Jiabing Leng +2
This paper addresses the challenge of generating high-quality academic charts that match the visual standards of human-authored papers. While existing AI agents can produce well-st…
cs.CV2026
Global Context Compression with Interleaved Vision-Text Transformation
Dian Jiao, Jiaxin Duan, Shuai Zhao +3
Recent achievements of vision-language models in end-to-end OCR point to a new avenue for low-loss compression of textual information. This motivates earlier works that render the…