Zining Wang

5

Papers

8

Total Citations

Papers (5)

A Token-level Text Image Foundation Model for Document Understanding

InstructOCR: Instruction Boosting Scene Text Spotting

Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding

Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes

Compressing Large Language Models by Joint Sparsification and Quantization