Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs 事件

Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs arXiv:2601.22709v4 Announce Type: replace Abstract: Vision-Language Models (VLMs) achieve strong multimodal performance but are costly to deploy, and post-training quantization often causes significant accuracy loss. Despite its potential, quantization-aware training for VLMs remains underexplored. We propose GRACE, a framework unifying knowledge distillation and QAT under the Information Bottleneck principle: quant