2 papers
cs.CV2026
Quant Experts: Token-aware Adaptive Error Reconstruction with Mixture of Experts for Large Vision-Language Models Quantization
Chenwei Jia, Baoting Li, Xuchong Zhang +3
Post-Training Quantization (PTQ) has emerged as an effective technique for alleviating the substantial computational and memory overheads of Vision-Language Models (VLMs) by compre…
cs.CV2023
Adversarial Score Distillation: When score distillation meets GAN
Min Wei, Jingkai Zhou, Junyao Sun +1
Existing score distillation methods are sensitive to classifier-free guidance (CFG) scale: manifested as over-smoothness or instability at small CFG scales, while over-saturation a…