2 papers
cs.AI2026
Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution
Jinwoo Chung, Jangho Kim
Mamba-based super-resolution models are efficient alternatives to Transformer-based restoration backbones, but their low-bit post-training quantization remains challenging because…
cs.LG2026
SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features
HyeonJun Lee, Hyeonsik Jo, Jinwoo Chung +1
Quantization-Aware Training (QAT) enables the deployment of quantized models with minimal accuracy degradation. However, in practical scenarios, training labels are often unavailab…