2026
Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs
ICML 2026poster
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 dis…