Yuan Cheng

SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression

Towards W2A4 LLM Inference: Hybrid SQ-VQ Framework with Adaptive Error Compensation

OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting

I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models