Chong Yu

5

Papers

62

Total Citations

Papers (5)

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer

Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression

Boosting Residual Networks with Group Knowledge

Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning

Once-Tuning-Multiple-Variants: Tuning Once and Expanded as Multiple Vision-Language Model Variants