When Better Teachers Don't Make Better Students: Revisiting Knowledge Distillation for CLIP Models in VQA
By: Pume Tuchinda , Parinthapat Pengpun , Romrawin Chumpu and more
Potential Business Impact:
Makes smart AI models smaller and faster.
Vision-language models (VLMs) have achieved remarkable success across multimodal tasks, yet their substantial computational demands hinder efficient deployment. Knowledge distillation (KD) has emerged as a powerful approach for building lightweight but competitive models, with strong evidence from both language and vision domains. However, its application to VLMs, particularly CLIP-style models, remains limited, often constrained to small-scale teachers and narrow evaluation tasks such as classification or retrieval. In this work, we present the first systematic study of distillation across a range of CLIP-style teacher models, ranging from standard baselines to large-scale state-of-the-art models. Contrary to trends observed in NLP and vision, we find that stronger teachers do not consistently yield better students; in fact, existing distillation frameworks often fail to scale, leading to degraded performance in downstream multimodal tasks such as visual question answering. Our findings challenge prevailing assumptions in KD and point toward new directions for designing parameter-efficient multimodal models.
Similar Papers
Enriching Knowledge Distillation with Cross-Modal Teacher Fusion
CV and Pattern Recognition
Teaches computers to learn better from many sources.
Distilling Multilingual Vision-Language Models: When Smaller Models Stay Multilingual
Computation and Language
Makes AI understand many languages better, even when smaller.
Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models
Computation and Language
Makes smart computer programs smaller and faster.