Knowledge Distillation Impact on CLIP Zero-Shot Retrieval and Inference Throughput

This report synthesises findings from 14 peer-reviewed papers addressing the following research question: How does knowledge distillation affect the zero-shot image-text retrieval accuracy and inference throughput of CLIP variants on the Flickr30k and MSCOCO datasets. Abstract The rapid evolution of large language models (LLMs) has driven a transformative shift in artificial intelligence (AI), reshaping both research paradigms and practical applications. Distinguished from their predecessors by unprecedented scale and advanced capabilities. 8 claims were extracted from source literature; 8 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.8/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does knowledge distillation affect the zero-shot image-text retrieval accuracy and inference throughput of CLIP variants on the Flickr30k and MSCOCO datasets?

Autonomous literature synthesis. Automated review score: 8.8/10. Full text and citation available at Assignee Research.